parsing - How to parse C# generic type names?

Question

How can I parse C#-style generic type names of the format List<int> or Dictionary<string,int> or even more complex Dictionary<string,Dictionary<System.String,int[]>>. Assume that these names are strings and may not actually represent existing types. It should just as easily be be able to parse BogusClass<A,B,Vector<C>>. To be clear, I am NOT interested in parsing .NET internal type names of the format List`1[[System.Int32]], but actual C# type names as they would appear in the source code, with or without namespace qualifiers using dot notation.

Regular expressions are out because these are nested structures. I thought perhaps the System.CodeDom.CodeTypeReference constructor would parse it for me since it has string BaseType and CodeTypeReferenceCollection TypeArguments members, but those apparently need to be set manually.

CodeTypeReference is the kind of structure I need:

class TypeNameStructure
{
    public string Name;
    public TypeNameStructure[] GenericTypeArguments;
    public bool IsGenericType{get;}
    public bool IsArray{get;} //would be nice to detect this as well

    public TypeNameStructure( string friendlyCSharpName )
    {
       //Parse friendlyCSharpName into name and generic type arguments recursively
    }
}

Are there any existing classes in the framework to achieve this kind of type name parsing? If not, how would I go about parsing this?

Answer 1

Answering own question. I wrote the following class achieve the results I need; give it a spin.

public class TypeName
{
    public string Name;
    public bool IsGeneric;
    public List<ArrayDimension> ArrayDimensions;
    public List<TypeName> TypeArguments;

    public class ArrayDimension
    {
        public int Dimensions;

        public ArrayDimension()
        {
            Dimensions = 1;
        }

        public override string ToString()
        {
            return "[" + new String(',', Dimensions - 1) + "]";
        }
    }

    public TypeName()
    {
        Name = null;
        IsGeneric = false;
        ArrayDimensions = new List<ArrayDimension>();
        TypeArguments = new List<TypeName>();
    }

    public static string MatchStructure( TypeName toMatch, TypeName toType )
    {
        return null;
    }

    public override string ToString()
    {
        string str = Name;
        if (IsGeneric)
            str += "<" + string.Join( ",", TypeArguments.Select<TypeName,string>( tn => tn.ToString() ) ) + ">";
        foreach (ArrayDimension d in ArrayDimensions)
            str += d.ToString();
        return str;
    }

    public string FormatForDisplay( int indent = 0 )
    {
        var spacing = new string(' ', indent );
        string str = spacing + "Name: " + Name + "
" +
        spacing + "IsGeneric: " + IsGeneric + "
" +
        spacing + "ArraySpec: " + string.Join( "", ArrayDimensions.Select<ArrayDimension,string>( d => d.ToString() ) ) + "
";
        if (IsGeneric)
        {
            str += spacing + "GenericParameters: {
" + string.Join( spacing + "},{
", TypeArguments.Select<TypeName,string>( t => t.FormatForDisplay( indent + 4 ) ) ) + spacing + "}
";
        }
        return str;
    }

    public static TypeName Parse( string name )
    {
        int pos = 0;
        bool dummy;
        return ParseInternal( name, ref pos, out dummy );
    }

    private static TypeName ParseInternal( string name, ref int pos, out bool listTerminated )
    {
        StringBuilder sb = new StringBuilder();
        TypeName tn = new TypeName();
        listTerminated = true;
        while (pos < name.Length)
        {
            char c = name[pos++];
            switch (c)
            {
                case ',':
                    if (tn.Name == null)
                        tn.Name = sb.ToString();
                    listTerminated = false;
                    return tn;
                case '>':
                    if (tn.Name == null)
                        tn.Name = sb.ToString();
                    listTerminated = true;
                    return tn;
                case '<':
                {
                    tn.Name = sb.ToString();
                    tn.IsGeneric = true;
                    sb.Length = 0;
                    bool terminated = false;
                    while (!terminated)
                        tn.TypeArguments.Add( ParseInternal( name, ref pos, out terminated ) );
                    var t = name[pos-1];
                    if (t == '>')
                        continue;
                    else
                        throw new Exception( "Missing closing > of generic type list." );
                }
                case '[':
                    ArrayDimension d = new ArrayDimension();
                    tn.ArrayDimensions.Add( d );
                analyzeArrayDimension: //label for looping over multidimensional arrays
                    if (pos < name.Length)
                    {
                        char nextChar = name[pos++];
                        switch (nextChar)
                        {
                            case ']':
                                continue; //array specifier terminated
                            case ',': //multidimensional array
                                d.Dimensions++;
                                goto analyzeArrayDimension;
                            default:
                                throw new Exception( @"Expecting ""]"" or "","" after ""["" for array specifier but encountered """ + nextChar + @"""." );
                        }
                    }
                    throw new Exception( "Expecting ] or , after [ for array type, but reached end of string." );
                default:
                    sb.Append(c);
                    continue;
            }
        }
        if (tn.Name == null)
            tn.Name = sb.ToString();
        return tn;
    }
}

If I run the following:

 Console.WriteLine( TypeName.Parse( "System.Collections.Generic.Dictionary<Vector<T>,int<long[]>[],bool>" ).ToString() );

It correctly produces the following output, representing the TypeName as a string:

Name: System.Collections.Generic.Dictionary
IsGeneric: True
ArraySpec:
GenericParameters: {
    Name: Vector
    IsGeneric: True
    ArraySpec:
    GenericParameters: {
        Name: T
        IsGeneric: False
        ArraySpec:
    }
},{
    Name: int
    IsGeneric: True
    ArraySpec: []
    GenericParameters: {
        Name: long
        IsGeneric: False
        ArraySpec: []
    }
},{
    Name: bool
    IsGeneric: False
    ArraySpec:
}